def searchAndSave(searchString, filename):
""" convenince function to search database and save
results to a FASTA file. If a file of that name
already exists then the whole process is skipped
searchString - this is what is being searched for
filename - name of the file where to save the results
"""
if not(path.isfile(filename)):
sequences = []
""" set of ids returned as part of the protein """
ids = seq.searchSequences(searchString)
print "Processing ", len(ids), " sequences ..."
""" iterate over the ids and for each fetch the record
from the database and append it to ex5_sequences
"""
for seq_id in ids:
print "Fetching sequence: ", seq_id
sequences.append(seq.getSequence(seq_id))
""" save the completed list of sequences to a FASTA file """
seq.writeFastaFile(filename, sequences)
else:
print filename, " exists. skipping."
seq2 = seq.Sequence('AAAAAGGGUG')
print seq2.alphabet
seq3 = seq.Sequence('AWAAAAAAGGVG')
print seq3.alphabet
#seq4 = seq.Sequence('Z')
#print seq3.alphabet
rns1 = seq.getSequence('RNS1_ARATH', 'uniprot')
print rns1.count('S')
#
ex5_ids = seq.searchSequences("signal+peptide+AND+organism:Arabidopsis+thaliana[3702]+AND+length:[100+TO+*]")
id6 = seq.searchSequences("Lipid+metabolism+AND+organism:3702+AND+fragment:no+AND+length:[100+TO+*]")
print "ID5: ", ex5_ids.__len__(), " ID6: ", id6.__len__()
to_be_written = []
ids = set(ex5_ids).intersection(set(id6))
print ids.__len__()
for i in ids:
pass
#s = seq.getSequence(i)
#to_be_written.append(s)
#print s
# iteritems???
#seq.writeFastaFile("results.fasta", to_be_written)